Skip to content
View fightheyyy's full-sized avatar
😸
vibe living
😸
vibe living
5 followers · 2 following

Achievements

Achievement: StarstruckAchievement: YOLOAchievement: Quickdraw

Achievements

Achievement: StarstruckAchievement: YOLOAchievement: Quickdraw

Block or report fightheyyy

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
fightheyyy/README.md

Hi! I am fightheyyy.
Agent Harness & Agentic Eval Developer.

website xiaoba cli

fightheyyy

Agent Harness & Agentic Eval Developer.

Agent Harness

XiaoBa-CLI as an agent runtime harness: sessions, tools, skills, roles, permissions, real workflow entrypoints, and a built-in observability / eval / regression layer with traces, replay, verifiers, and scorecards.

Agentic Eval

Arena-style evaluation for reusable agent capabilities: clean runtime overlays, low-context UserCat E2E runs, InspectorCat issue extraction, and ReviewerCat multi-attempt replay scorecards before promotion.

Pinned Loading

  1. CATENA CATENA Public

    Trace-driven Agent evolution, E2E evaluation, regression replay, and release control plane.

    Go

  2. xiaobaOS xiaobaOS Public

    Local-first, IM-native AI coworker runtime with async role agents, trace replay, evidence, and agentic evaluation.

    TypeScript 15 1

  3. gauzmem gauzmem Public

    GauzMem: traceable memory service for AI agents with semantic, graph, and temporal recall. Self-hosted with MySQL, Qdrant, Neo4j, Redis, and MinIO.

    Python 2

  4. barena barena Public

    Agentic evaluation and release framework for AI agents — run, replay, verify, and gate skills, roles, prompts, tools, and runtime changes.

    TypeScript

  5. fightheyyy.github.io fightheyyy.github.io Public

    HTML

  6. SuperCoding SuperCoding Public

    SuperGoal, SuperDev, and SuperReview: three Codex skills for acceptance-first goals, architecture-aligned AI coding, and main-agent code review with atomic repairs.

    Shell